Created by: nihuizhidao

CentOS 7 CUDA 10.0 paddlepaddle 1.8.1.post107 paddlehub 1.7.1 face_landmark_localization==1.0.2 pyramidbox_lite_server==1.1.0

在运行下面代码时：

shaper = hub.Module(name="face_landmark_localization")
shaper.set_face_detector_module(hub.Module(name="pyramidbox_lite_server"))
......
detected_keypoints = shaper.keypoint_detection(images=[frame], use_gpu=True)  # frame is cv2.imread() object

出现以下错误：

W0827 03:06:23.397197 50265 device_context.cc:252] Please NOTE: device: 0, CUDA Capability: 75, Driver API Version: 11.0, Runtime API Version: 10.0 W0827 03:06:23.401690 50265 device_context.cc:260] device: 0, cuDNN Version: 7.6. [2020-08-27 03:06:25,641] [ INFO] - Installing face_landmark_localization module [2020-08-27 03:06:25,739] [ INFO] - Module face_landmark_localization already installed in /home/scc/.paddlehub/modules/face_landmark_localization [2020-08-27 03:06:25,740] [ INFO] - Installing ultra_light_fast_generic_face_detector_1mb_640 module [2020-08-27 03:06:25,753] [ INFO] - Module ultra_light_fast_generic_face_detector_1mb_640 already installed in /home/scc/.paddlehub/modules/ultra_light_fast_generic_face_detector_1mb_640 [2020-08-27 03:06:26,325] [ INFO] - Installing pyramidbox_lite_server module [2020-08-27 03:06:26,355] [ INFO] - Module pyramidbox_lite_server already installed in /home/scc/.paddlehub/modules/pyramidbox_lite_server Process Process-3: Traceback (most recent call last): File "/home/scc/anaconda3/envs/paddle/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap self.run() File "/home/scc/anaconda3/envs/paddle/lib/python3.7/multiprocessing/process.py", line 99, in run self._target(*self._args, **self._kwargs) File "get_infer_results_pp.py", line 205, in infer_process detected_keypoints = shaper.keypoint_detection(images=[frame], use_gpu=True) # BGR mode, need by paddlehub File "/home/scc/.paddlehub/modules/face_landmark_localization/module.py", line 141, in keypoint_detection for yield_data in reader(self.face_detector, images, paths, use_gpu): File "/home/scc/.paddlehub/modules/face_landmark_localization/data_feed.py", line 48, in reader visualization=False)): TypeError: call() missing 1 required positional argument: 'data'

请问这个是什么原因呢？

P.S.，代码里使用了多线程，这些代码都在子线程里